CtrlK
BlogDocsLog inGet started
Tessl Logo

caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

95

1.39x
Quality

92%

Does it follow best practices?

Impact

99%

1.39x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is caveman in JuliusBrussee/caveman

SKILL.md
Quality
Evals
Security

Quality

Content

90%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable instruction skill that embodies its own brevity principle and gives concrete rules plus per-level worked examples. Weakest only on workflow sequencing and progressive disclosure, which are largely non-applicable to a single-purpose style skill with no bundle files.

Suggestions

Tighten the Auto-Clarity handoff into an explicit check (e.g., 'Before responding: scan for security warnings / irreversible ops / ambiguous compression → if any, drop caveman for that part, resume after') to make the workflow sequence explicit.

Consider extracting the two multi-level worked examples into a references/EXAMPLES.md so SKILL.md stays a lean overview pointing one level deep, which would also raise progressive_disclosure.

DimensionReasoningScore

Conciseness

Lean and self-demonstrating: no padding, no explaining concepts Claude already knows, and every example earns its place by illustrating a distinct intensity level. The skill practices the brevity it teaches.

5 / 5

Actionability

Concrete, executable guidance: exact drop-lists (articles/filler/pleasantries/hedging), a fixed output pattern, before/after pairs, and worked per-level examples across two domains — fully actionable for an instruction-only skill.

5 / 5

Workflow Clarity

The single action is unambiguous and the Auto-Clarity section supplies drop-caveman checkpoints, but there is no explicit validation sequence; the 'resume caveman after clear part done' handoff is slightly implicit rather than a checked step.

4 / 5

Progressive Disclosure

Well-organized into clear sections (Persistence, Rules, Intensity, Auto-Clarity, Boundaries) with no nested references and no content that clearly belongs in a separate file, but there are no one-level-deep references to signal (none are needed), so it sits just below the split-reference anchor.

4 / 5

Total

18

/

20

Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that concretely states what the skill does and gives explicit, natural trigger phrases plus a slash command. Minor room to sharpen the action verbs, but it clearly satisfies both the 'what' and 'when' requirements.

DimensionReasoningScore

Specificity

Names concrete capabilities ('Cuts token usage ~75%', 'keeping full technical accuracy') and comprehensively enumerates six intensity levels, but the actions are feature/mode descriptions rather than a list of distinct action verbs, leaving a minor gap versus the comprehensive-anchor.

4 / 5

Completeness

Explicitly answers both what (ultra-compressed mode cutting ~75% tokens while preserving technical accuracy with six levels) and when ('Use when user says...') with concrete trigger phrases, in third person.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases including synonyms ('caveman mode', 'talk like caveman', 'use caveman', 'less tokens', 'be brief'), the /caveman slash command, and the 'token efficiency' phrasing.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (caveman-style compression) with distinctive triggers unlikely to fire for unrelated skills; minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
masweb/waxp-vuebo
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.